Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases indicating accountability or legal obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    izo
    -0.17
    ongo
    -0.17
    ibile
    -0.14
    artz
    -0.14
    úa
    -0.14
    emann
    -0.14
    oust
    -0.14
     oby
    -0.14
    arde
    -0.13
    PCS
    -0.13
    POSITIVE LOGITS
    Repositories
    0.15
    icl
    0.14
     clue
    0.14
    롯
    0.14
    aticon
    0.14
    ora
    0.14
     accommodations
    0.14
    ulo
    0.13
    aise
    0.13
     رب
    0.13
    Act Density 0.231%

    No Known Activations